Molecular graph enhanced transformer for retrosynthesis prediction

Mao, Kelong; Xiao, Xi; Xu, Tingyang; Rong, Yu; Huang, Junzhou; Zhao, Peilin

doi:10.1016/j.neucom.2021.06.037

Cited by 37 publications

(37 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This simple strategy has been demonstrated to be a powerful method in terms of graph expression and structure information extraction. Details regarding graph transformers can be found elsewhere (Mao et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

Artificial intelligence-based gas chromatography-olfactometry for sensory evaluation of key compounds in food ingredients

Shang

Liu

Tang

et al. 2022

Preprint

View full text Add to dashboard Cite

The prediction of structure-odor-relationship (SOR) by deep neural networks (DNN) via the structural features of odorants has attracted great attention during the past decade. Due to the limited knowledge on binding mechanism between odorant molecules and olfactory receptors, however, it is not sure what kind of structural features play the most important role in smell recognition. Here, diverse DNNs, including molecular parameters neural network, molecular graphic convolution neural network (MG-CNN), molecular graph transformer neural network, and atom interaction neural network, were used to extract the structure features of molecules and to predict the categorized odor perception. The experimental results demonstrated that an MG-CNN combined with a multi-label DNN classifier produced the best results, with an area under the receiver operating characteristic curve and F1-score of 0.877±0.028 and 0.726±0.028, respectively. This is the first systematic study for molecular structure features extracted by different deep neural network and their predictive effect for SOR. We believe that these insights regarding the use of DNN-based odorant molecular feature extraction for odor sensory identification will be useful for introducing biologically interpretable artificial intelligence into olfactometry, and thus contribute to our understanding of the mechanisms underlying human olfaction.

show abstract

Section: Methodsmentioning

confidence: 99%

Artificial intelligence-based gas chromatography-olfactometry for sensory evaluation of key compounds in food ingredients

Shang

Liu

Tang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To provide a synthetic strategy directly from ML predictions, many ML models are trained with organic chemical reaction databases. Thanks to well‐structured large‐scale organic chemical reaction database, large ML models become trainable [19,20] . The first type of ML studies to figure out synthetic routes is to quantify the reactivity and the second category is an optimization of reaction.…”

Section: Synthetic Routesmentioning

confidence: 99%

“…Thanks to well-structured large-scale organic chemical reaction database, large ML models become trainable. [19,20] The first type of ML studies to figure out synthetic routes is to quantify the reactivity and the second category is an optimization of reaction. The last one is retrosynthesis which aims to directly find the starting materials and series of backward reactions from a target material.…”

Section: Synthetic Routesmentioning

confidence: 99%

“…In contrast to the great advances in ML methods to handle chemical compounds, ML studies for chemical reactions, another main subject of chemistry, have been relatively less active due to the lack of data. Recently, with the aid of data‐mining and high‐throughput simulations, chemists can build reaction data libraries beyond lab‐scale or manually constructed reaction databases [19,20] . Those stimulate ML applications in chemical reactions.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, with the aid of datamining and high-throughput simulations, chemists can build reaction data libraries beyond lab-scale or manually constructed reaction databases. [19,20] Those stimulate ML applications in chemical reactions. In addition to the size of databases, standardization of chemical reactions are another problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Applications for Chemical Reactions

Park

Han

Choi

2022

Chemistry An Asian Journal

View full text Add to dashboard Cite

Machine learning (ML) approaches have enabled rapid and efficient molecular property predictions as well as the design of new novel materials. In addition to great success for molecular problems, ML techniques are applied to various chemical reaction problems that require huge costs to solve with the existing experimental and simulation methods. In this review, starting with basic representations of chemical reactions, we summarized recent achievements of ML studies on two different problems; predicting reaction properties and synthetic routes. The various ML models are used to predict physical properties related to chemical reaction properties (e. g. thermodynamic changes, activation barriers, and reaction rates). Furthermore, the predictions of reactivity, self-optimization of reaction, and designing retrosynthetic reaction paths are also tackled by ML approaches. Herein we illustrate various ML strategies utilized in the various context of chemical reaction studies.

show abstract